Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification

TL;DR

This paper introduces a fully unsupervised hierarchical clustering approach for person re-identification that leverages pseudo labels and PK sampling, achieving state-of-the-art results on multiple datasets.

Contribution

It proposes a novel hierarchical clustering-guided re-ID method that trains solely on unlabeled target data using pseudo labels and PK sampling to improve unsupervised re-ID performance.

Findings

Achieves 55.3% mAP on Market-1501

Achieves 46.8% mAP on DukeMTMC-reID

Outperforms existing unsupervised methods

Abstract

For most unsupervised person re-identification (re-ID), people often adopt unsupervised domain adaptation (UDA) method. UDA often train on the labeled source dataset and evaluate on the target dataset, which often focuses on learning differences between the source dataset and the target dataset to improve the generalization of the model. Base on these, we explore how to make use of the similarity of samples to conduct a fully unsupervised method which just trains on the unlabeled target dataset. Concretely, we propose a hierarchical clustering-guided re-ID (HCR) method. We use hierarchical clustering to generate pseudo labels and use these pseudo labels as monitors to conduct the training. In order to exclude hard examples and promote the convergence of the model, We use PK sampling in each iteration, which randomly selects a fixed number of samples from each cluster for training. We evaluate our model on Market-1501, DukeMTMC-reID and MSMT17. Results show that HCR gets the state-of-the-arts and achieves 55.3% mAP on Market-1501 and 46.8% mAP on DukeMTMC-reID. Our code will be released soon.